Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@pdf4me-mcp Merge these two PDFs into one document"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
PDF4me MCP Server provides PDF4me API functionality through the Model Context Protocol (MCP), enabling AI assistants to easily perform a wide range of PDF, document, image, and barcode processing tasks.
PDF → Office: Convert PDFs to Word (DOCX), Excel (XLSX), PowerPoint (PPTX)
PDF → Other Formats: Convert PDFs to PDF/A, searchable OCR PDF, HTML, Markdown
Office → PDF: Convert DOCX, PPTX, XLSX, CSV, HTML, Markdown, Visio, and images to PDF
Word → PDF Form: Convert Word documents into fillable PDF forms
JSON → Excel: Convert JSON data files into Excel workbooks
Stamps & Watermarks: Add text or image stamps/watermarks to PDFs
Headers & Footers: Inject HTML-based headers and footers
Annotations: Add page numbers, margins, hyperlink annotations
Attachments: Embed any file as an attachment inside a PDF
Signing: Apply signature images to PDF pages
Find & Replace: Search and replace text, or replace text with images
Merge: Combine multiple PDFs or overlay two PDFs
Split: Split by page, page range, barcode, Swiss QR code, or matching text
Delete / Extract: Remove or extract specific pages, delete blank pages
Rotate: Rotate all pages or selected pages of a PDF
Form Data: Extract values from fillable PDF form fields
Tables: Detect and extract tables with coordinates
Text: Extract text by regex expression; find and replace text
Attachments: Pull embedded file attachments out of a PDF
Resources: Extract text and images from PDF content
Classification: Classify a PDF by document type, category, and confidence
Invoices, Orders, Receipts: Structured data extraction using AI
Bank Statements & Cheques: Parse financial documents automatically
Contracts & Mortgage Documents: Extract key fields from legal documents
Tax Documents & Pay Stubs: Parse tax forms and payroll documents
ID & Cards: Process health cards, credit cards, marriage certificates, and shipping labels
Universal Extraction: Generic AI data extraction from any document type
Create: Generate barcodes and QR codes (PNG)
Add to PDF: Stamp a barcode or QR code onto PDF pages
Read from PDF / Image: Detect and decode barcodes and QR codes
Swiss QR Bill: Create and read Swiss QR Bill payment sections; split PDFs by Swiss QR
Format Conversion: Convert between BMP, GIF, JPG, PNG, TIFF
Editing: Resize, rotate, flip, and crop images
Watermarks: Add image or text watermarks to images
OCR: Extract text from images using OCR
Metadata: Read or strip EXIF metadata
Compression: Compress images with configurable quality levels
Track Changes: Enable, disable, or extract tracked changes in Word documents
Replace Text with Image: Substitute text placeholders with images in Word
Extract Text: Pull text from Word documents with header/footer and comment control
Single Document: Generate one document from a template and data (JSON, XML, or plain text)
Batch Documents: Generate multiple documents from a single template and dataset
Protect PDF: Apply password protection with configurable permissions
Unlock PDF: Remove password protection from a PDF
ZUGFeRD Invoice: Create standards-compliant ZUGFeRD e-invoices (XML or PDF+XML)
Upload File: Upload local files to PDF4me cloud storage
PDF Metadata: Read full metadata (title, author, page count, security info, dates)
Image Metadata: Read image properties and EXIF fields
Repair PDF: Repair corrupted or malformed PDFs
Optimize PDF: Compress, linearize (web-optimize), or flatten PDFs
Related MCP server: MCP PDF
Sign up at dev.pdf4me.com
Get your API key from the dashboard
You need UV (a fast Python packaging tool) to run this MCP server.
macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | shWindows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"Alternative methods
# Homebrew (macOS)
brew install uv
# pipx
pipx install uv
# pip
pip install uvFor more options, see the UV installation guide.
Open Cursor Settings → MCP, or edit ~/.cursor/mcp.json (macOS/Linux) / %USERPROFILE%\.cursor\mcp.json (Windows):
{
"mcpServers": {
"pdf4me-mcp": {
"command": "uvx",
"args": ["pdf4me-mcp"],
"env": {
"API_KEY": "your-api-key-here"
}
}
}
}Open the Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"pdf4me-mcp": {
"command": "uvx",
"args": ["pdf4me-mcp"],
"env": {
"API_KEY": "your-api-key-here"
}
}
}
}Open ~/.config/Code/User/mcp.json (macOS/Linux) or %APPDATA%\Code\User\mcp.json (Windows):
{
"servers": {
"pdf4me-mcp": {
"type": "stdio",
"command": "uvx",
"args": ["pdf4me-mcp"],
"env": {
"API_KEY": "your-api-key-here"
}
}
}
}Edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"pdf4me-mcp": {
"command": "uvx",
"args": ["pdf4me-mcp"],
"env": {
"API_KEY": "your-api-key-here"
}
}
}
}Add to your ~/.continue/config.json:
{
"mcpServers": [
{
"name": "pdf4me-mcp",
"command": "uvx",
"args": ["pdf4me-mcp"],
"env": {
"API_KEY": "your-api-key-here"
}
}
]
}On Windows, uvx may need to be called with its full path if it is not on your PATH. Replace "command": "uvx" with the full path, e.g.:
"command": "C:\\Users\\<YourUser>\\.local\\bin\\uvx"Tool | Description |
| Draw a barcode or QR code onto PDF pages with configurable alignment and size |
| Generate a barcode or QR code as a PNG image (supports Code128, QR, and more) |
| Read and decode barcode/QR data from a local PDF with barcode type and page filtering |
| Detect and decode barcodes and QR codes from a local image file |
| Add a Swiss QR Bill payment section to a PDF (IBAN, creditor details, currency, reference) |
| Parse and extract Swiss QR Bill payment data from a local PDF |
| Split a PDF into multiple files at pages that contain a specific barcode value or type |
| Split a PDF by Swiss QR code positions into separate PDF files or a ZIP archive |
Tool | Description |
| Convert documents (DOCX, PPTX, XLSX, images, text formats) to PDF |
| Convert a local HTML file to PDF with layout, margins, and print options |
| Convert a web page URL to PDF with auth, layout, and margin settings |
| Convert a local Markdown file to PDF |
| Convert a Visio file (.vsdx/.vsd/.vsdm) to PDF |
| Convert a Word document (DOCX) into a fillable PDF form |
| Convert a PDF to DOCX with quality settings, language, and optional OCR |
| Convert a PDF to XLSX with quality, merge sheets, language, and optional OCR |
| Convert a PDF to PPTX with quality, language, and optional OCR |
| Convert a PDF to PDF/A (PdfA1a through PdfA3u) with upgrade/downgrade control |
| Make a scanned PDF searchable by running OCR and embedding a text layer |
| Convert a local JSON file to an Excel workbook (XLSX) with worksheet name and title options |
| Convert images between BMP, GIF, JPG, PNG, and TIFF formats |
| Flatten a PDF (merge form fields and annotations into the page content) |
| Linearize (web-optimize) a PDF for fast browser loading with configurable optimization presets |
Tool | Description |
| Embed one or more files as attachments inside a PDF |
| Add an HTML-formatted header, footer, or both to PDF pages |
| Add page margins (in millimeters) to all pages of a PDF |
| Insert page numbers with configurable alignment, format, and font styling |
| Place an image stamp or watermark on PDF pages with alignment, opacity, and size controls |
| Place a text stamp or watermark on PDF pages with font, opacity, rotation, and alignment options |
| Apply a signature image to a PDF with layout and margin options |
| Find and replace text across PDF pages |
| Replace text occurrences in a PDF with an image at configurable dimensions |
| Update or replace hyperlink annotations in a PDF by search criteria |
| Repair a corrupted or malformed PDF file |
Tool | Description |
| Extract specific pages from a PDF into a new PDF file |
| Extract all form field names and their current values from a PDF |
| Extract embedded file attachments from a PDF and save them to disk |
| Extract text content and images embedded in a PDF |
| Detect and extract tables from a PDF, saving results as JSON and CSV |
| Extract text from a PDF using a regular expression pattern |
| Extract text from a Word document, with options to remove headers, footers, or comments |
| Extract text from an image using OCR |
| Classify a PDF by document type and category with a confidence score |
| Extract structured data from a PDF using a predefined PDF4me parsing template |
Tool | Description |
| Add new TextBox or CheckBox form fields to a PDF at specified coordinates |
| Fill existing form fields in a PDF using a key/value data map |
Tool | Description |
| Generate one document from a template (DOCX/HTML/PDF) and a data payload (JSON/XML/text) |
| Generate multiple documents in batch from one template and a multi-record dataset |
| Enable Track Changes mode in a Word document |
| Disable Track Changes mode in a Word document |
| Extract all tracked change data from a Word document as structured JSON |
| Replace text placeholders in a Word document with an image |
Tool | Description |
| Overlay a watermark image onto another image with opacity and position controls |
| Add a text watermark to an image with font, color, opacity, and rotation options |
| Compress a JPG, PNG, or WebP image with configurable compression level |
| Convert an image between BMP, GIF, JPG, PNG, and TIFF formats |
| Render PDF pages to image files (JPEG, PNG, TIFF) with page selection and width options |
| Crop an image by border or by a specific rectangle region |
| Flip an image horizontally or vertically |
| Extract image properties and EXIF metadata from a JPG or PNG file |
| Run OCR on an image to extract its text content |
| Resize an image by percentage or to specific dimensions, with aspect ratio control |
| Rotate an image by a specified angle with background color and resize options |
| Auto-rotate an image to its correct orientation based on its EXIF metadata |
| Strip all EXIF metadata from a JPG or PNG image |
Tool | Description |
| Merge two or more PDF files into a single PDF |
| Overlay one PDF on top of another (e.g. stamp a letterhead) |
| Split a PDF by page number, recurring interval, sequence, or page ranges |
| Split a PDF at pages containing a specified barcode |
| Split a PDF at Swiss QR code positions |
| Split a PDF at pages containing a specific text string |
Tool | Description |
| Compress a PDF with optimization profiles for Web, Print, or Screen |
| Remove blank pages from a PDF (no text, no images, or both) |
| Linearize a PDF for fast incremental loading in web browsers |
Tool | Description |
| Remove specific pages from a PDF by page number or range |
| Extract selected pages from a PDF into a new file |
| Rotate all pages of a PDF (Clockwise, CounterClockwise, UpsideDown) |
| Rotate selected pages of a PDF independently |
Tool | Description |
| Read full PDF metadata: title, author, page count, security info, and dates |
| Read image properties and available EXIF fields from a JPG or PNG |
| Attempt to repair a corrupted or malformed PDF |
Tool | Description |
| Password-protect a PDF with configurable permissions (print, copy, edit, etc.) |
| Remove password protection from a PDF using the current password |
Tool | Description |
| Extract structured invoice data (line items, totals, dates, vendor info) from a PDF or image using AI |
| Parse bank cheque images and extract cheque details using AI |
| Extract key clauses and fields from contract documents using AI |
| Extract credit card information from card images using AI |
| Extract data from health insurance card images using AI |
| Extract fields from marriage certificates using AI, with optional authenticity verification |
| Extract key financial and property details from mortgage documents using AI |
| Extract earnings, deductions, and employee details from pay stub documents using AI |
| Parse bank statements for transactions, balances, and patterns using AI |
| Extract order details (items, quantities, prices, addresses) from purchase order documents using AI |
| Extract merchant info, line items, and totals from receipt images or PDFs using AI |
| Extract carrier, tracking number, and address data from shipping labels using AI |
| Extract tax form fields and computed values from tax documents using AI |
| Extract any specified fields from any document type using AI (configurable field list) |
Tool | Description |
| Create a ZUGFeRD-compliant e-invoice from XML, JSON, or CSV data — as PDF+XML or XML-only |
Tool | Description |
| Upload a local file to PDF4me cloud storage and receive a file reference for further operations |
| Register a webhook callback URL to receive documents from PDF4me |
Convert a PDF to Word:
Convert this PDF to a Word document: /path/to/document.pdfMerge multiple PDFs:
Merge these PDFs into one: report.pdf, appendix.pdf, cover.pdfExtract invoice data using AI:
Extract all invoice details from this file: invoice.pdfAdd a Swiss QR Bill to a PDF:
Add a Swiss QR Bill to invoice.pdf with IBAN CH93-0076-2011-6238-5295-7, creditor name "Acme AG"Split a PDF by barcode:
Split this PDF at every page containing a Code128 barcode: batch.pdfGenerate a document from a template:
Generate a contract PDF from contract_template.docx with this data: {"client": "ACME", "date": "2024-01-01"}Compress an image:
Compress this PNG image with maximum compression: photo.pngOCR a scanned PDF:
Make this scanned PDF searchable: scanned_report.pdfuvx pdf4me-mcpOr, if installed locally:
API_KEY=your-api-key-here pdf4me-mcpPDF4me: pdf4me.com
API Documentation: docs.pdf4me.com
Issue Reports: GitHub Issues
This project is distributed under the MIT License.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Document API for AI-native software: render PDFs, e-sign, PAdES-seal, and verify.
Turn any PDF into structured JSON via AI + OCR: invoices, bank statements, contracts.
Turn a description into a shareable, editable PDF — invoices, certificates, reports, resumes.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/pdf4me/pdf4me-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server